Adversarial Noise Isolation in Multimodal Perception: A Computational Framework Inspired by Inhibitory Control
Open Access
- 30 May 2026
- journal article
- research article
- Published by MDPI AG in Brain Sciences
- Vol. 16 (6) , 591
Abstract
Background: Robust perception involves processing heterogeneous sensory signals, such as facial expressions, vocal prosody, and language, particularly in noisy environments. In computational modeling, a key challenge is integrating these diverse inputs while actively filtering uninformative variations. While recent deep learning models address this integration through complex fusion architectures, they typically aggregate features without explicit filtering modules analogous to inhibitory control. In this study, we propose Multi-modal Information Disentanglement (MInD), a computational framework designed to test the hypothesis that algorithmic noise isolation facilitates robust multisensory integration. Methods: Drawing conceptual inspiration from cognitive theories of modularity, our model decomposes sensory inputs into amodal (modality-invariant) and modal-specific pathways. Furthermore, we introduce an adversarial noise isolation mechanism to serve as an algorithmic analog to cognitive inhibition. Given that our model operates on pre-extracted high-level features, this mechanism functions to isolate latent distributional variance—uninformative fluctuations that persist after initial feature extraction—guiding the network to separate task-relevant affective cues from irrelevant feature variance. Results: Empirical evaluations on standard emotion recognition benchmarks indicate that this purification-before-fusion strategy is associated with competitive performance and stability across multiple metrics. Notably, the framework attains these results using simple linear integration layers, suggesting that separating representations prior to fusion may reduce the computational complexity required for subsequent integration. Conclusions: These observations highlight the computational utility of algorithmic noise suppression, illustrating how cognitive inspiration can inform efficient machine learning architectures without claiming direct neurobiological validation.Keywords
Funding Information
- National Natural Science Foundation of China (U22B2063)
- National Science and Technology Innovation 2030 Project of China (2021ZD0202600)
This publication has 31 references indexed in Scilit:
- Adaptive Cross-Modal Denoising: Enhancing LiDAR–Camera Fusion Perception in Adverse CircumstancesSensors, 2026
- Contrastive-Based Removal of Negative Information in Multimodal Emotion AnalysisCognitive Computation, 2025
- RViT: Robust Fusion Vision Transformer with Variational Hierarchical Denoising Process for Image ClassificationGuidance, Navigation and Control, 2024
- Self-HCL: Self-Supervised Multitask Learning with Hybrid Contrastive Learning Strategy for Multimodal Sentiment AnalysisElectronics, 2024
- TCHFN: Multimodal sentiment analysis based on Text-Centric Hierarchical Fusion NetworkKnowledge-Based Systems, 2024
- AOBERT: All-modalities-in-One BERT for multimodal sentiment analysisInformation Fusion, 2022
- Multimodal Sentiment Intensity Analysis in Videos: Facial Gestures and Verbal MessagesIEEE Intelligent Systems, 2016
- The multifaceted interplay between attention and multisensory integrationTrends in Cognitive Sciences, 2010
- Humans integrate visual and haptic information in a statistically optimal fashionNature, 2002
- Vision. A Computational Investigation Into the Human Representation and Processing of Visual Information. David MarrThe Quarterly Review of Biology, 1983